标题： Newfluence：在高维空间中提升模型可解释性和理解能力 显示英文标题

标题： Newfluence: Boosting Model interpretability and Understanding in High Dimensions

摘要： 随着机器学习（ML）和人工智能（AI）模型的复杂性不断增加，对于帮助科学家、工程师和政策制定者解释和优化模型决策和预测的工具的需求变得越来越迫切。 影响函数起源于稳健统计学，已成为一种流行的方法。 然而，影响函数的启发式基础依赖于低维假设，其中参数数量$p$远小于观测数量$n$。 相比之下，现代AI模型通常在高维环境中运行，具有较大的$p$，这挑战了这些假设。 在本文中，我们研究了高维环境下影响函数的准确性。 我们的理论和实证分析表明，影响函数无法可靠地实现其预期目的。 然后，我们引入了一种替代近似方法，称为Newfluence，它在保持相似计算效率的同时提供了显著改进的准确性。 预计Newfluence将为解释复杂AI模型和诊断其问题提供比许多现有方法更准确的见解。 此外，本文中开发的高维框架也可以用于分析其他流行的技巧，例如Shapley值。 显示英文摘要

摘要： The increasing complexity of machine learning (ML) and artificial intelligence (AI) models has created a pressing need for tools that help scientists, engineers, and policymakers interpret and refine model decisions and predictions. Influence functions, originating from robust statistics, have emerged as a popular approach for this purpose. However, the heuristic foundations of influence functions rely on low-dimensional assumptions where the number of parameters $p$ is much smaller than the number of observations $n$. In contrast, modern AI models often operate in high-dimensional regimes with large $p$, challenging these assumptions. In this paper, we examine the accuracy of influence functions in high-dimensional settings. Our theoretical and empirical analyses reveal that influence functions cannot reliably fulfill their intended purpose. We then introduce an alternative approximation, called Newfluence, that maintains similar computational efficiency while offering significantly improved accuracy. Newfluence is expected to provide more accurate insights than many existing methods for interpreting complex AI models and diagnosing their issues. Moreover, the high-dimensional framework we develop in this paper can also be applied to analyze other popular techniques, such as Shapley values.